AgentIndex

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It does disclose the concrete payload (score, delivery/honesty rates, latency, recent probes, chain-aware payment receipts), which is useful, but it says nothing about cost/latency of probing, auth requirements, rate limits, or whether the tool triggers live probes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler: the report contents come first and the identifier formats second. Every clause earns its place and the most important information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no annotations, the description does the necessary work by naming the fields returned and both accepted identifier forms. What is missing is operational context (whether probes hit the network, cost, or permissions), but for a simple two-parameter read tool it is nearly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100%, so the baseline is 3, but the description goes beyond it by giving concrete identifier examples ('weatherpro' label vs 'weatherpro.agentindex.eth' full name), which disambiguates the two accepted formats. It says nothing extra about the probes count parameter, which is already bounded and documented in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource (a full trust report for one named service) and enumerates the report contents (score, delivery/honesty rates, latency, probes, payment receipts), which clearly separates it from discovery-oriented siblings like find_service. The retrieval verb is only implied rather than named, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by 'for one service' and by the accepted identifier forms, so an agent can infer this is the single-service lookup vs. find_service. However, there is no explicit when-to-use/when-not guidance, no mention of prerequisites, and no named alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It usefully discloses the return contents (endpoints, prices, probed trust scores) and the implied read-only nature of a search, but says nothing about cost, auth, rate limits, or result limits/pagination for a live registry query.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences: the first states the action and the search criterion, the second states the return payload. Nothing is padded and the purpose is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly summarizes the returned fields (endpoints, prices, trust scores), covering the main gap. Minor omissions remain around result volume, pagination, and failure behavior, but nothing essential to invoking the tool is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the single 'need' parameter, so the baseline is 3. The description goes beyond the schema by supplying two concrete example queries, which clarifies that the parameter is a free-text capability description rather than a structured identifier and helps the agent phrase the value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource ('Search the AgentIndex registry for x402 services') and names the matching criterion ('matching a capability'), so the tool's function is unambiguous. It stops short of differentiating itself from siblings such as check_trust or resolve_data_need, which an agent must infer from names alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Concrete query examples ('weather data', 'token prices') imply when the tool is appropriate, and the registry-search framing makes the context reasonably clear. However, there is no statement of when NOT to use it or which sibling (resolve_data_need, get_verified_data) should be preferred under what conditions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it does disclose the return payload shape (data + trust score + probe receipt) and the provider-selection policy (scam/low-trust never selected). It does not cover auth needs, cost/latency, rate limits, or what happens when no trusted provider is found, which are meaningful gaps for a tool with zero annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, each doing distinct work: what it returns, when to use it, and the trust-selection guarantee. The core action is front-loaded with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Since there is no output schema, the description correctly spells out what comes back (data, trust score, probe receipt), and with no annotations it supplies the key behavioral guarantee about provider selection. It is still silent on failure behavior when no sufficiently trusted provider exists and on cost/latency, leaving minor gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single `need` parameter is already documented with concrete examples ("current ETH price", "weather in Singapore"). The description adds nothing about the parameter beyond framing it as the resolved need, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a concrete composite action: select the most-trusted provider for a need, fetch data from it, and return the data plus the provider's trust score and on-chain probe receipt. The phrase "One call" implicitly contrasts it with the multi-step path through siblings like find_service/check_trust/resolve_data_need. It stops short of naming those siblings explicitly, so the differentiation is inferred rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Use when you want the answer AND a record of why the source was trusted" gives a clear selection condition, with the added constraint that scam/low-trust providers are never selected. However, it never states when NOT to use this tool or when to prefer the sibling tools (find_service, check_trust, resolve_data_need) instead.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden. It usefully discloses the output shape (best pick, ranked alternatives, avoid list), which tells the agent this is a recommendation/decision step. It does not say whether the call itself costs anything, whether it is read-only, or how it behaves with ambiguous tasks.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences, front-loaded with the core value ('describe a task, get back the single best service') and finished with the usage cue. Every clause earns its place and nothing is repeated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description compensates by summarizing the return (best service, ranked alternatives, avoid list). For a single-parameter decision tool that is close to sufficient; only cost/latency or ambiguity-handling details are missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single 'task' parameter already carries an example, so the schema does the heavy lifting. The description adds nothing to parameter semantics beyond implying that the task string drives the selection. Baseline 3 is appropriate for a one-param tool with full schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb+resource ('selection', 'describe a task') and states the concrete deliverable: the single best service to pay, ranked alternatives, and services to avoid. It is clear about what the tool returns, but it never mentions the sibling tools (find_service, check_trust, get_verified_data), so an agent must infer how it differs from find_service on its own.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a concrete trigger: 'Use this before spending money over x402.' That is a real when-to-use signal rather than vague context. However, it offers no exclusions and does not name an alternative tool for cases where the agent just wants to browse or check trust instead.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.